H0 or No?
This is the statement that there is no effect, no difference, or no association.
What is the Null Hypothesis H0?
This ratio compared the risk in the exposed group to the risk in the unexposed group.
What is relative risk (RR)?
This is the value you calculate from your sample data and compare to a critical value to decide whether to reject H0.
What is the test statistic?
A correlation coefficient value of 0.99 between two variables implies that one variable has a strong causal relationship with the other variable.
What is False? Correlation does NOT mean causation.
You want to test whether two categorical variables are related in a single sample (e.g., smoking status and disease status). Which test should you use?
What is the chi-square test of independence?
If your p-value is less than the alpha level, you make this decision.
What is reject the null hypothesis?
This ratio compares the odds of an outcome in the exposed group to the odds in the unexposed group.
What is the odds ratio (OR)?
This value, chosen before the test, represents the probability of making a Type 1 error.
What is the significance level?
The coefficient of determination is the square of the correlation coefficient.
What is True?
You have a small sample and want to test the mean of one group against a hypothesized population mean. The population standard deviation is not given. What test should you use?
What is a one-sample t-test?
This type of error happens when you reject H0 even though it's actually true.
What is a Type 1 Error?
If an RR = 1.0, this is what it means about the association between exposure and outcome.
What is no association?
This test is appropriate for comparing a sample mean to a known population mean when the population standard deviation is unknown.
What is the one-sample t-test?
The IQR is a better measure of variation than the standard deviation when the data is normally distributed.
What is False?
You measure the same individuals twice (before and after an intervention) and want to compare their means. What test should you use?
What is the paired t-test?
You want to know if the average systolic BP in a population is different from 120 mmHg. This is the type of hypothesis test you would use.
What is a two-sided one-sample t-test?
A study finds OR = 3.2 for smoking and asthma. Interpret this in words.
What is the odds of asthma are 3.2 times higher in smokers than non-smokers?
A researcher wants to test whether a new study technique changes exam scores. The average score last year was 78. Write the null and alternative hypotheses for this test.
What is:
H0: u = 78
HA: u ≠ 78
The inference space is determined by the population.
What is True?
You want to check whether the observed counts in one categorical variable match a set of expected proportions. Which test is appropriate?
What is the chi-square goodness-of-fit test?
In hypothesis testing, this value is the largest significance level at which you would still fail to reject H0. It is often directly reported in R output.
What is the p-value?
In a cohort study, 15 out of 100 exposed individuals develop a disease, and 30 out of 300 unexposed individuals develop it. Compute the relative risk (RR).
What is (15/100) / (30/300) = 0.15 / 0.10 = 1.5?
This term refers to the probability of correctly rejecting the null hypothesis when it is false.
What is statistical power?
Two samples are said to be independent if P(A|B) = P(A)P(B).
What is False? If independent, P(A|B) = P(A).
You want to compare the means of three or more independent groups to see if at least one mean differs. What statistical test do you use?
What is one-way ANOVA?